Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    fibonacci sequence or proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وأن
    1.66
     raff
    1.61
    lerine
    1.60
    )"
    1.50
     CQ
    1.49
     apparatus
    1.46
     and
    1.43
    יות
    1.43
    ,
    1.43
    見る
    1.41
    POSITIVE LOGITS
     maî
    2.22
    EN
    2.09
    ྜ
    2.05
    LE
    2.03
    IRE
    1.99
    assurer
    1.98
    pubescens
    1.97
    SE
    1.95
    ILLS
    1.95
     coû
    1.91
    Act Density 0.088%

    No Known Activations